In this paper, we implement a deep learning model to identify associations between microRNAs and drug resistance. The proposed model employs kmer algorithms, autoencoders, and mol2vec for sequence embedding, and utilizes datasets that are meticulously...
In this paper, we implement a deep learning model to identify associations between microRNAs and drug resistance. The proposed model employs kmer algorithms, autoencoders, and mol2vec for sequence embedding, and utilizes datasets that are meticulously filtered based on Euclidean distance, cosine similarity, and Mahalanobis distance for negative data selection. The features of this data are then integrated using a CNN and analyzed for patterns using a Bi-LSTM. This approach allows for a comprehensive understanding of the multidimensional characteristics of the data and enables reliable predictions.